Data-Assistive Course Articulation Using Machine Translation

Abstract
Higher education, such as in the California public post-secondary system, has promoted upward socioeconomic mobility by supporting student transfer from 2-year community colleges to 4-year degree granting universities. Among the barriers to transfer is earning enough credit at 2-year institutions that qualify for the transfer credit required by 4-year degree programs. Course articulation is defining how course credit earned outside of an institution maps to course credit within the institution, and it is an intractable task when attempting to manually articulate all courses among the colleges and universities in a state. In this talk, based on best paper work published at Learning @ Scale, I will present a methodology towards making tractable this process of defining and maintaining articulations by leveraging information contained within historic enrollment patterns and course catalog descriptions. I will provide a proof-of-concept analysis using data from a 4-year and 2-year institution to predict articulation pairs between them, produced from language translation models and validated on a set of 65 institutionally pre-established course-to-course articulations. Validation results suggest that historic enrollments contain novel information about course content not found in the catalog description. The accuracy of the model is not yet high enough to reliably identify articulations without human supervision; however, it can successfully narrow the candidates for articulation down to a more manageable set than was previously possible without considerable manual effort. Limitations and an implementation pilot of this approach will be discussed as well as future directions for algorithmic improvement.

Zachary Pardos is an Assistant Professor at the University of California, Berkeley in the Graduate School of Education and School of Information. He directs the Computational Approaches to Human Learning research lab and teaches courses on data mining and analytics, the history of digital learning environments, and machine learning in education. His focal areas of study are knowledge representation and personalized supports leveraging big data in education.

Date: 
Tuesday, February 18, 2020 - 2:00pm
Building: 
Berkeley Way West
Room: 
1215
AttachmentSize
PDF icon Presentation slides754.33 KB